2692-2967ISSN (Online)
2770-0216ISSN (Print)
Stock market direction prediction becomes an essential task in the business sector. The inherent volatile behavior of stock markets worldwide makes the prediction process difficult. The improvement in the prediction accuracy of the stock market direction prediction helps to avoid the risks involved in the investment process. In this aspect, this study designs a swallow swarm optimization (SSO) with a fuzzy support vector machine (FSVM) model for stock market direction prediction. The proposed SSO-FSVM model encompasses preprocessing, feature extraction, FSVM, and SSO based parameter tuning. The usage of the SSO algorithm to fine-tune the parameters involved in the FSVM model helps to significantly improve the overall predictive performance. To validate the improved performance of the SSO-FSVM model, a wide range of experiments were carried out using two benchmark datasets. The experimental outcomes reported the betterment of the SSO-FSVM model over the recent approaches in terms of several evaluation metrics.
Read MoreDoi: https://doi.org/10.54216/AJBOR.060102
Vol. 6 Issue. 1 PP. 23-35, (2022)
Recent innovation in business intelligence (BI) assists companies to stay successful and competitive with the increasing business trend. Businesses have started to examine the succeeding level of data analytics and BI solution. At the same time, Customer Churn Prediction (CCP) is an essential procedure involved in business decision making that effectually determines the churn of clients and performs adequate processes to retain customers. With this motivation, this paper presents a sandpiper optimization with the bidirectional gated recurrent unit (SPO-BiGRU) for CCP on BI applications. The SPO-BiGRU model aims for determining the occurrence of customers into churners or non-churner. In addition, the SPO-BiGRU technique involves pre-processing, classification, and hyperparameter optimization. Followed by, the BiGRU model is applied to perform the predictive process. At last, the SPO algorithm is applied to optimally adjust the hyperparameters involved in the BiGRU model. For validating the enhanced performance of the SPO-BiGRU method, a wide range of simulations take place and the results are inspected under varying aspects. The experimental results portrayed the supremacy of the SPO-BiGRU technique over the recent state of art approaches.
Read MoreDoi: https://doi.org/10.54216/AJBOR.060103
Vol. 6 Issue. 1 PP. 36-47, (2021)
The main goal of the paper is to determine the factors affecting the student’s academic achievements at the University of Peshawar. This study would help the students and teachers to identify the factors that improve the academic achievements of the students. A descriptive type of questionnaire was designed to gathered information from 264 students studying in various departments at the University of Peshawar, Pakistan. The study focuses on different factors including socio-economic factors, teacher’s effectiveness and methodology of their teaching, social media, and the use of mobile phones, and parental factors. Chi-square statistics were used to study the impact of factors affecting the student academic achievements. The analysis concluded that except for the gender under socio-economic factors, teacher experience under teacher effectiveness factors, parent relationship with the student and their family income under parental factors, and the use of social media and mobile phones all the factors have an impact on the student academic achievements.
Read MoreDoi: https://doi.org/10.54216/AJBOR.060104
Vol. 6 Issue. 1 PP. 48-55, (2022)
This paper proposes Asymmetric coordination strategy, we study coordinated search technique for a lost located object on the plan, where there are two searchers beginning their search from the same initial point (0, 0), but both sides do not have the same area. Here we introduce a model of search plan and investigate the expected value of detecting the lost target in both sides to avoid wasting time. We present an algorithm to facilitate the search technique. An illustrative application from real life has been introduced to demonstrate the applicability of this search technique. The effectiveness of this model has been illustrated by numerical results
Read MoreDoi: https://doi.org/10.54216/AJBOR.060105
Vol. 6 Issue. 1 PP. 56-71, (2022)
Residual tensions from manufacturing components and equipment assembly, functional job loads (fixed and dynamic loads), and the disrupted exploitation process all cause strains on bucket-wheel excavators in use (non-stationary dynamic loads). For the purpose of deciding which bucket wheel excavator (BWE) should participate in the rehabilitation and modernisation process, this study proposes a technique for assessing and rating BWEs. In this context, we use a multicriteria approache. The MCDM approach, including the Additive Ratio Assessment, is examined in this work (ARAS). The model, derived from MCDM procedures, are used to the task of assessing the primary metrics that define a BWE's performance. Each cluster of factors, together with their subparameters and potential values, will be subjected to the procedures. There are two sections to the model definitions. Using the ARAS technique, the first section identifies the parameters of most importance and defines their respective priority vectors. In the second section, options are analysed and ranked in accordance with the established criteria using a different set of techniques. The benefits were shown from two perspectives in the paper's findings. The first part is creating a framework that can be used to address other issues with the same structure. There's also the actual machine selection, which is based on a complicated examination of many different variables. In most cases, the model generalises well and may be re-used in future studies with comparable parameters.
Read MoreDoi: https://doi.org/10.54216/AJBOR.060106
Vol. 6 Issue. 1 PP. 72-84, (2022)